Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical values related to offline activities

    oai_token-act-pair · gpt-3.5-turbo

    references to online activity metrics and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     whisk
    -0.75
    fitting
    -0.70
     recount
    -0.70
     crib
    -0.70
     whistle
    -0.69
     wind
    -0.69
    ways
    -0.68
     substitute
    -0.67
     palm
    -0.67
     circulation
    -0.66
    POSITIVE LOGITS
    Activity
    1.45
    edIn
    1.03
     Activity
    1.02
    ertodd
    0.97
    ukong
    0.92
    Instance
    0.89
    Compat
    0.89
    Thread
    0.88
     Activities
    0.86
    ð
    0.86
    Act Density 0.019%

    No Known Activations